65 citations · 162 across the 14 of their papers we have counts for
14 papers
Geometric Neural Diffusion Processes
Emile Mathieu, Vincent Dutordoir, Michael J. Hutchinson +3
Denoising diffusion models have proven to be a flexible and effective paradigm for generative modelling. Their recent extension to infinite dimensional Euclidean spaces has allowed…
Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
Louis C. Tiao, Vincent Dutordoir, Victor Picheny
Despite their many desirable properties, Gaussian processes (GPs) are often compared unfavorably to deep neural networks (NNs) for lacking the ability to learn representations. Rec…
Memory-Based Meta-Learning on Non-Stationary Distributions
Tim Genewein, Grégoire Delétang, Anian Ruoss +7
Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log l…
Neural Diffusion Processes
Vincent Dutordoir, Alan Saul, Zoubin Ghahramani +1
Neural network approaches for meta-learning distributions over functions have desirable properties such as increased flexibility and a reduced complexity of inference. Building on…
Deep Neural Networks as Point Estimates for Deep Gaussian Processes
Vincent Dutordoir, James Hensman, Mark van der Wilk +3
Neural networks and Gaussian processes are complementary in their strengths and weaknesses. Having a better understanding of their relationship comes with the promise to make each…
GPflux: A Library for Deep Gaussian Processes
Vincent Dutordoir, Hugh Salimbeni, Eric Hambro +7
We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the v…
A Tutorial on Sparse Gaussian Processes and Variational Inference
Felix Leibfried, Vincent Dutordoir, ST John +1
Gaussian processes (GPs) provide a framework for Bayesian inference that can offer principled uncertainty estimates for a large range of problems. For example, if we consider regre…
Sparse Gaussian Processes with Spherical Harmonic Features
Vincent Dutordoir, Nicolas Durrande, James Hensman
We introduce a new class of inter-domain variational Gaussian processes (GP) where data is mapped onto the unit hypersphere in order to use spherical harmonic representations. Our…
Automatic Tuning of Stochastic Gradient Descent with Bayesian Optimisation
Victor Picheny, Vincent Dutordoir, Artem Artemev +1
Many machine learning models require a training procedure based on running stochastic gradient descent. A key element for the efficiency of those algorithms is the choice of the le…
Scalable Thompson Sampling using Sparse Gaussian Process Models
Sattar Vakili, Henry Moss, Artem Artemev +2
Thompson Sampling (TS) from Gaussian Process (GP) models is a powerful tool for the optimization of black-box functions. Although TS enjoys strong theoretical guarantees and convin…
A Framework for Interdomain and Multioutput Gaussian Processes
Mark van der Wilk, Vincent Dutordoir, ST John +3
One obstacle to the use of Gaussian processes (GPs) in large-scale problems, and as a component in deep learning system, is the need for bespoke derivations and implementations for…
Deep Gaussian Processes with Importance-Weighted Variational Inference
Hugh Salimbeni, Vincent Dutordoir, James Hensman +1
Deep Gaussian processes (DGPs) can model complex marginal densities as well as complex mappings. Non-Gaussian marginals are essential for modelling real-world data, and can be gene…
Bayesian Image Classification with Deep Convolutional Gaussian Processes
Vincent Dutordoir, Mark van der Wilk, Artem Artemev +1
In decision-making systems, it is important to have classifiers that have calibrated uncertainties, with an optimisation objective that can be used for automated model selection an…
Gaussian Process Conditional Density Estimation
Vincent Dutordoir, Hugh Salimbeni, Marc Deisenroth +1
Conditional Density Estimation (CDE) models deal with estimating conditional distributions. The conditions imposed on the distribution are the inputs of the model. CDE is a challen…